Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description still adds meaningful behavior: pagination semantics ('at most 50 per page', 'Read the next page with next_cursor'), deterministic category ordering, and the handler field distinguishing well vs member. It also explains the multi-workspace refusal behavior ('this read will not guess which one you mean'), which is exactly the kind of surprising behavior an agent needs warned about.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with the resource definition and pagination, then the workspace-scoping rule. Zero filler sentences, though the item-field enumeration overlaps with the output schema and could be trimmed without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-shape explanation is not strictly needed, yet the description's field list is a useful map of the payload. Pagination, ordering, workspace scoping, and the well/member handler distinction are all covered. The one remaining gap is that neither the description nor the call guidance says what to do with resolve_with or when this listing should be preferred over other worklist-oriented siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3 and the schema already documents limit, cursor, workspace_id, conversation_id, and workspace_scope. The description adds real behavioral meaning for two of them — next_cursor as the pagination continuation and workspace_id's required-when-multiple-workspaces rule — but stays silent on conversation_id and workspace_scope, which the schema carries alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the live accounting items of the workspace') and immediately defines what an accounting item is: 'the open work the accounting review gathers', in category order, capped at 50 per page. It also enumerates what each item carries (category, decision, resolve_with, references, web_url, handler), so the agent knows exactly what it is retrieving. This is clearly separable from siblings like well_get_worklist_status or well_list_unposted_transactions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditional guidance for the workspace question: call directly when the token authorizes one workspace, pass workspace_id when it authorizes several. That is a real when/when-not rule an agent would otherwise get wrong. It stops short of naming sibling alternatives (e.g., when to use resolve_with targets vs. this listing) or stating exclusions, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.